CN-122003889-A - Communication method, communication device, communication system, storage medium, and program product

Abstract

The embodiment of the disclosure relates to a communication method, a communication device, a communication system, a storage medium and a program product. The communication method can be performed by a first node and comprises the steps of obtaining first information, determining a second node for providing the first AI reasoning service according to the first information, and sending second information, wherein the second information is used for indicating the second node to provide the first AI reasoning service. In the disclosure, the second node is matched with the first information, so that the second node can meet the requirement of the first AI reasoning service on computing capacity and resources, and no extra delay is brought.

Inventors

• LIU JIANNING

Assignees

• 北京小米移动软件有限公司

Dates

Publication Date

20260508

Application Date

20240906

Claims (20)

1. A method of communication, performed by a first node, the method comprising: Acquiring first information, wherein the first information is used for requesting a first artificial intelligence AI reasoning service; Determining a second node for providing the first AI reasoning service according to the first information; and sending second information, wherein the second information is used for indicating the second node to provide the first AI reasoning service.
2. The method of claim 1, wherein the first information comprises at least one of: the first indication information is used for indicating a fourth node requesting the first AI reasoning service; the second indication information is used for indicating the quality requirement of the first AI reasoning service; The third indication information is used for indicating the model requirement of the first AI reasoning service; Fourth indication information for indicating a type of the first AI reasoning service; fifth indication information for indicating a position of the fourth node; and sixth indication information, configured to indicate a service area of the first AI reasoning service.
3. The method according to claim 1 or 2, wherein the determining a second node for providing the first AI reasoning service from the first information comprises: And determining a second node from the plurality of third nodes according to the first information and third information related to the plurality of third nodes, wherein the plurality of third nodes are nodes for providing AI reasoning services.
4. A method according to claim 3, wherein the third information comprises at least one of: Seventh indication information for indicating the supporting capability of the third node to different types of AI reasoning services; Eighth indication information, configured to indicate a supporting capability of the third node to an AI model; ninth indication information, configured to indicate the third node to process a resource of the AI reasoning service; Tenth indication information for indicating the position of the third node.
5. The method according to claim 1 or 2, wherein the determining a second node for providing the first AI reasoning service from the first information comprises: determining the second node according to the first information and eleventh indication information; The eleventh indication information is used for indicating the mapping relation between the type of the AI reasoning service and the second node.
6. The method of any one of claims 1 to 5, wherein the method further comprises one of: Determining a first reasoning method adopted by the first AI reasoning service according to the first information; Determining a first reasoning method adopted by the first AI reasoning service according to the first information and the twelfth indication information; The twelfth indication information is used for indicating the mapping relation between the type of the AI reasoning service and the reasoning method.
7. The method of claim 6, wherein the second information is further for instructing the second node to provide the first AI reasoning service using the first reasoning method.
8. The method of any of claims 1-7, wherein the number of second nodes is a plurality, the method further comprising: Determining a plurality of reasoning tasks associated with the first AI reasoning service; the plurality of inference tasks are assigned to the plurality of second nodes.
9. The method of any of claims 1 to 8, wherein the second information comprises at least one of: The first information; thirteenth indication information for indicating the first AI reasoning service; fourteenth instruction information for instructing a plurality of inference tasks associated with the first AI reasoning service; Fifteenth instruction information for instructing a first inference method employed by the first AI reasoning service.
10. The method of any of claims 1 to 9, wherein the second information is further used to request a data connection to be established between the second node and a fourth node.
11. The method of claim 10, wherein the method further comprises: receiving fourth information sent by the second node, wherein the fourth information is used for indicating an access address of the second node; And sending fifth information to the fourth node, wherein the fifth information comprises the fourth information.
12. The method of claim 11, wherein the number of second nodes is a plurality, the fifth information further comprising: Sixteenth indication information, configured to indicate a mapping relationship between the reasoning task associated with the first AI reasoning service and the second node.
13. The method of any of claims 1 to 12, wherein the first node and the second node are deployed on the same device.
14. A method of communication performed by a second node, the method comprising: And receiving second information sent by the first node, wherein the second information is used for indicating the second node to provide a first AI reasoning service, the second node is determined by the first node according to the first information, and the first information is used for requesting the first AI reasoning service.
15. The method of claim 14, wherein the first information comprises at least one of: the first indication information is used for indicating a fourth node requesting the first AI reasoning service; the second indication information is used for indicating the quality requirement of the first AI reasoning service; The third indication information is used for indicating the model requirement of the first AI reasoning service; Fourth indication information for indicating a type of the first AI reasoning service; fifth indication information for indicating a position of the fourth node; and sixth indication information, configured to indicate a service area of the first AI reasoning service.
16. The method of claim 14 or 15, wherein the second node is determined by the first node from a plurality of third nodes, which are nodes for providing AI reasoning services, according to the first information and third information associated with the plurality of third nodes.
17. The method of claim 16, wherein the third information comprises at least one of: Seventh indication information for indicating the supporting capability of the second node to different types of AI reasoning services; Eighth indication information, configured to indicate a supporting capability of the second node to an AI model; ninth indication information, configured to indicate the second node to process a resource of the AI reasoning service; tenth indication information for indicating the position of the second node.
18. The method of claim 14 or 15, wherein the second node is determined by the first node according to the first information and eleventh indication information, where the eleventh indication information is used to indicate a mapping relationship between a type of AI reasoning service and the second node.
19. The method of any of claims 14 to 18, wherein the second information is further used to instruct the second node to provide the first AI reasoning service using a first reasoning method.
20. The method of claim 19, wherein the first inference method is derived based on the first information or the first inference method is derived based on the first information and twelfth indication information indicating a mapping relationship of a type of the AI reasoning service and a reasoning method.

Description

Communication method, communication device, communication system, storage medium, and program product Technical Field The present disclosure relates to the field of communication technologies, and in particular, to a communication method, a communication device, a communication system, a storage medium, and a program product. Background As communication technology advances, artificial intelligence (ARTIFICIAL INTELLIGENCE, AI), machine learning (MACHINE LEARNING, ML) or other models have been introduced into communication systems. Through the models, data reasoning or prediction can be performed in scenes such as automatic driving, medical assistance, cross-device calculation, digital twinning and the like. Disclosure of Invention In the process of model reasoning, on one hand, the terminal cannot support reasoning services exceeding the calculation capability of the terminal due to the limited calculation capability of the terminal, and on the other hand, although a third-party server can be adopted to provide the reasoning services for the terminal, the terminal also brings additional delay and influences user experience. The embodiment of the disclosure provides a communication method, a communication device, a communication system, a storage medium and a program product. According to a first aspect of an embodiment of the disclosure, a communication method is provided and executed by a first node, the method includes obtaining first information, the first information being used for requesting a first artificial intelligence AI reasoning service, determining a second node for providing the first AI reasoning service according to the first information, and sending second information, the second information being used for indicating the second node to provide the first AI reasoning service. According to a second aspect of the embodiments of the present disclosure, a communication method is provided and performed by a second node, the method including receiving second information sent by a first node, the second information being used to instruct the second node to provide a first AI reasoning service, the second node being determined by the first node according to the first information, the first information being used to request the first AI reasoning service. According to a third aspect of the disclosed embodiments, a communication method is provided, performed by a fourth node, the method comprising sending first information to a first node, the first information being for requesting a first AI reasoning service, the first AI reasoning service being provided by a second node, the second node being determined by the first node from the first information. According to a fourth aspect of the embodiments of the present disclosure, a first node is provided, which includes a first transceiver module configured to obtain first information, where the first information is used to request a first artificial intelligence AI reasoning service, send second information, where the second information is used to instruct a second node to provide the first AI reasoning service, and a first processing module configured to determine the second node for providing the first AI reasoning service according to the first information. According to a fifth aspect of the embodiments of the present disclosure, a second node is provided, including a second transceiver module configured to receive second information sent by a first node, where the second information is used to instruct the second node to provide a first AI reasoning service, and the second node is determined by the first node according to the first information, where the first information is used to request the first AI reasoning service. According to a sixth aspect of the embodiments of the present disclosure, there is provided a fourth node comprising a third transceiver module configured to send first information to a first node, the first information being for requesting a first AI reasoning service provided by a second node, the second node being determined by the first node from the first information. According to a seventh aspect of embodiments of the present disclosure, a communication device is presented, comprising one or more processors, wherein the communication device is adapted to perform the communication method as in any of the first to third aspects. According to an eighth aspect of an embodiment of the present disclosure, a communication system is presented, comprising a first node, a second node and a fourth node, the first node being configured to implement a communication method as in the first aspect, the second node being configured to implement a communication method as in the second aspect, the fourth node being configured to implement a communication method as in the third aspect. According to a ninth aspect of the embodiments of the present disclosure, a storage medium is presented, the storage medium storing instructions that, when run on a